A multiple-imputation metropolis version of the EM algorithm

被引：14
|
作者：
Gaetan, C
Yao, JF
机构：
[1] Univ Padua, Dipartimento Sci Stat, I-35121 Padua, Italy
[2] Univ Rennes 1, IRMAR, F-35042 Rennes, France
来源：
BIOMETRIKA | 2003年 / 90卷 / 03期
关键词：
incomplete data; mixed model; multiple imputation; simulated annealing; Stochastic FM;
D O I：
10.1093/biomet/90.3.643
中图分类号：
Q [生物科学];
学科分类号：
07 ; 0710 ; 09 ;
摘要：
In this paper we introduce a new stochastic variant of the EM algorithm. The algorithm combines the principle of multiple imputation and the theory of simulated annealing to deal with cases where the E-step and the M-step can be intractable or numerically inefficient.
引用
收藏
页码：643 / 654
页数：12
相关论文
共 50 条
12345